Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 19459
    Prev
    Next
    INDEX
    Explanations

    references to town hall meetings and associated activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to meetings, government, and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    fires on a noun followed by a quantity, often in an American political context

    Explanation Uploaded by User

    number/quantity skipgram

    Explanation Uploaded by User
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Skip Features
    number skipgram
    •contextual features
    fires on noun following quantity in political context

    No Comments

    Negative Logits
    ĸļ
    -0.93
    bsite
    -0.69
    anwhile
    -0.65
    leneck
    -0.60
    epad
    -0.59
    ropolis
    -0.59
    ité
    -0.58
     Spiel
    -0.58
     Barkley
    -0.57
    uria
    -0.57
    POSITIVE LOGITS
     variants
    1.02
     varieties
    0.99
    isations
    0.93
     types
    0.92
     instances
    0.92
     equivalents
    0.92
     implementations
    0.91
    types
    0.90
     cases
    0.90
     categories
    0.90
    Activations Density 0.808%

    No Known Activations